© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110886
    Prev
    Next
    INDEX
    Explanations

    suicide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Region
    -0.08
     před
    -0.07
    균
    -0.07
    理论
    -0.07
     neighboring
    -0.07
     REGION
    -0.07
    озмож
    -0.07
     region
    -0.07
    争
    -0.07
     Region
    -0.07
    POSITIVE LOGITS
     suicide
    0.08
    189
    0.08
     sweep
    0.08
    achim
    0.07
     humming
    0.07
    -agent
    0.07
     booth
    0.07
    ائمة
    0.07
     aso
    0.07
     cassette
    0.07
    Activations Density 0.004%

    No Known Activations